Search

Biomedical image segmentation plays a vital role in diagnosis of diseases across various organs. Deep learning-based object detection methods are commonly used for such segmentation. There exists an extensive research in this topic. However, there is no standard review on this topic. Existing surveys often lack a standardized approach or focus on broader segmentation techniques. In this paper, we conducted a systematic literature review (SLR), collected and analysed 148 articles that explore deep learning object detection methods for biomedical image segmentation. We critically analyzed these methods, identified the key challenges, and discussed the future directions. From the selected articles we extracted the results including the deep learning models, targeted imaging modalities, targeted diseases, and the metrics for the analysis of the methods. The results have been presented in tabular and/or charted forms. The results are presented in three major categories including two stage detection models, one stage detection models and point-based detection models. Each article is individually analyzed along with its pros and cons. Finally, we discuss open challenges, potential benefits, and future research directions. This SLR aims to provide the research community with a quick yet deeper understanding of these segmentation models, ultimately facilitating the development of more powerful solutions for biomedical image analysis.

Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data. However, most of the current VQA models use datasets that are primarily focused on English and a few major world languages, with images that are typically Western-centric. While recent efforts have tried to increase the number of languages covered on VQA datasets, they still lack diversity in low-resource languages. More importantly, although these datasets often extend their linguistic range via translation or some other approaches, they usually keep images the same, resulting in narrow cultural representation. To address these limitations, we construct CVQA, a new Culturally-diverse multilingual Visual Question Answering benchmark, designed to cover a rich set of languages and cultures, where we engage native speakers and cultural experts in the data collection process. As a result, CVQA includes culturally-driven images and questions from across 28 countries on four continents, covering 26 languages with 11 scripts, providing a total of 9k questions. We then benchmark several Multimodal Large Language Models (MLLMs) on CVQA, and show that the dataset is challenging for the current state-of-the-art models. This benchmark can serve as a probing evaluation suite for assessing the cultural capability and bias of multimodal models and hopefully encourage more research efforts toward increasing cultural awareness and linguistic diversity in this field.

Cascading failures, triggered by a local perturbation, can be catastrophic and cause irreparable damages in a wide area. Hence, blocking the devastating cascades is an important issue in real world networks. One of the ways to control the cascade is to use protective measures, so that the agents decide to be protected against failure. Here, we consider a coevolution of the linear threshold model for the spread of cascading failures and a decision-making game based on the perceived risk of failure. Protected agents are less vulnerable to failure and in return the size of the cascade affects the agent's decision to get insured. We find at what range of protection efficiency and cost of failure, the global cascades stop. Also we observe that in some range of protection efficiency, a bistable region emerges for the size of cascade and the prevalence of protected agents. Moreover, we show how savings or the ability of agents to repair can prevent cascades from occurring, Comment: 8 pages, 6 figures

The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objects, and interpreting their changes as conveyed through language. Traditional methods, which isolate object captioning and state change detection, offer a limited view of dynamic environments. Moreover, relying on a small set of symbolic words to represent changes has restricted the expressiveness of the language. To address these challenges, in this paper, we introduce the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs). Our experiments demonstrate that while MLLMs show some skill, they lack a full understanding of object state changes. The benchmark includes a fine-tuned model that, despite initial capabilities, requires significant improvements in accuracy and generalization ability for effective understanding of these changes. Our code and dataset are available at https://github.com/nguyennm1024/OSCaR., Comment: NAACL 2024

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image segmentation. There are numerous types of CNNs designed to meet specific needs and requirements, including 1D, 2D, and 3D CNNs, as well as dilated, grouped, attention, depthwise convolutions, and NAS, among others. Each type of CNN has its unique structure and characteristics, making it suitable for specific tasks. It's crucial to gain a thorough understanding and perform a comparative analysis of these different CNN types to understand their strengths and weaknesses. Furthermore, studying the performance, limitations, and practical applications of each type of CNN can aid in the development of new and improved architectures in the future. We also dive into the platforms and frameworks that researchers utilize for their research or development from various perspectives. Additionally, we explore the main research fields of CNN like 6D vision, generative models, and meta-learning. This survey paper provides a comprehensive examination and comparison of various CNN architectures, highlighting their architectural differences and emphasizing their respective advantages, disadvantages, applications, challenges, and future trends.

Video description entails automatically generating coherent natural language sentences that narrate the content of a given video. We introduce CLearViD, a transformer-based model for video description generation that leverages curriculum learning to accomplish this task. In particular, we investigate two curriculum strategies: (1) progressively exposing the model to more challenging samples by gradually applying a Gaussian noise to the video data, and (2) gradually reducing the capacity of the network through dropout during the training process. These methods enable the model to learn more robust and generalizable features. Moreover, CLearViD leverages the Mish activation function, which provides non-linearity and non-monotonicity and helps alleviate the issue of vanishing gradients. Our extensive experiments and ablation studies demonstrate the effectiveness of the proposed model. The results on two datasets, namely ActivityNet Captions and YouCook2, show that CLearViD significantly outperforms existing state-of-the-art models in terms of both accuracy and diversity metrics., Comment: 15 pages, 4 figures

Afghanistan has witnessed many armed conflicts throughout history, especially in the past 20 years; these events have had a significant impact on human lives, including military and civilians, with potential fatalities. In this research, we aim to leverage state-of-the-art machine learning techniques to classify the outcomes of Afghanistan armed conflicts to either fatal or non-fatal based on their textual descriptions provided by the Armed Conflict Location & Event Data Project (ACLED) dataset. The dataset contains comprehensive descriptions of armed conflicts in Afghanistan that took place from August 2021 to March 2023. The proposed approach leverages the power of BERT (Bidirectional Encoder Representations from Transformers), a cutting-edge language representation model in natural language processing. The classifier utilizes the raw textual description of an event to estimate the likelihood of the event resulting in a fatality. The model achieved impressive performance on the test set with an accuracy of 98.8%, recall of 98.05%, precision of 99.6%, and an F1 score of 98.82%. These results highlight the model's robustness and indicate its potential impact in various areas such as resource allocation, policymaking, and humanitarian aid efforts in Afghanistan. The model indicates a machine learning-based text classification approach using the ACLED dataset to accurately classify fatality in Afghanistan armed conflicts, achieving robust performance with the BERT model and paving the way for future endeavors in predicting event severity in Afghanistan., Comment: 6 pages, 4 figures, 2 tables

Available works addressing multi-label classification in a data stream environment focus on proposing accurate models; however, these models often exhibit inefficiency and cannot balance effectiveness and efficiency. In this work, we propose a neural network-based approach that tackles this issue and is suitable for high-dimensional multi-label classification. Our model uses a selective concept drift adaptation mechanism that makes it suitable for a non-stationary environment. Additionally, we adapt our model to an environment with missing labels using a simple yet effective imputation strategy and demonstrate that it outperforms a vast majority of the state-of-the-art supervised models. To achieve our purposes, we introduce a weighted binary relevance-based approach named ML-BELS using the Broad Ensemble Learning System (BELS) as its base classifier. Instead of a chain of stacked classifiers, our model employs independent weighted ensembles, with the weights generated by the predictions of a BELS classifier. We show that using the weighting strategy on datasets with low label cardinality negatively impacts the accuracy of the model; with this in mind, we use the label cardinality as a trigger for applying the weights. We present an extensive assessment of our model using 11 state-of-the-art baselines, five synthetics, and 13 real-world datasets, all with different characteristics. Our results demonstrate that the proposed approach ML-BELS is successful in balancing effectiveness and efficiency, and is robust to missing labels and concept drift.

Let $G$ be a graph. A total dominating set in a graph $G$ is a set $S$ of vertices of $G$ such that every vertex in $G$ is adjacent to a vertex in $S$. Recently, the following question was proposed: "Is it true that every connected cubic graph containing a $3$-cycle has two vertex disjoint total dominating sets?" In this paper, we give a negative answer to this question. Moreover, we prove that if we replace $3$-cycle with $4$-cycle the answer is affirmative. This implies every connected cubic graph containing a diamond (the complete graph of order $4$ minus one edge) as a subgraph can be partitioned into two total dominating sets, a result that was proved in 2017.

Ensembles, which employ a set of classifiers to enhance classification accuracy collectively, are crucial in the era of big data. However, although there is general agreement that the relation between ensemble size and its prediction accuracy, the exact nature of this relationship is still unknown. We introduce a novel perspective, rooted in the linear independence of classifier's votes, to analyze the interplay between ensemble size and prediction accuracy. This framework reveals a theoretical link, consequently proposing an ensemble size based on this relationship. Our study builds upon a geometric framework and develops a series of theorems. These theorems clarify the role of linear dependency in crafting ensembles. We present a method to determine the minimum ensemble size required to ensure a target probability of linearly independent votes among component classifiers. Incorporating real and synthetic datasets, our empirical results demonstrate a trend: increasing the number of classifiers enhances accuracy, as predicted by our theoretical insights. However, we also identify a point of diminishing returns, beyond which additional classifiers provide diminishing improvements in accuracy. Surprisingly, the calculated ideal ensemble size deviates from empirical results for certain datasets, emphasizing the influence of other factors. This study opens avenues for deeper investigations into the complex dynamics governing ensemble design and offers guidance for constructing efficient and effective ensembles in practical scenarios.

Ensemble methods are commonly used in classification due to their remarkable performance. Achieving high accuracy in a data stream environment is a challenging task considering disruptive changes in the data distribution, also known as concept drift. A greater diversity of ensemble components is known to enhance prediction accuracy in such settings. Despite the diversity of components within an ensemble, not all contribute as expected to its overall performance. This necessitates a method for selecting components that exhibit high performance and diversity. We present a novel ensemble construction and maintenance approach based on MMR (Maximal Marginal Relevance) that dynamically combines the diversity and prediction accuracy of components during the process of structuring an ensemble. The experimental results on both four real and 11 synthetic datasets demonstrate that the proposed approach (DynED) provides a higher average mean accuracy compared to the five state-of-the-art baselines., Comment: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM '23), October 21--25, 2023, Birmingham, United Kingdom

Representation learning methods have revolutionized machine learning on networks by converting discrete network structures into continuous domains. However, dynamic networks that evolve over time pose new challenges. To address this, dynamic representation learning methods have gained attention, offering benefits like reduced learning time and improved accuracy by utilizing temporal information. T-batching is a valuable technique for training dynamic network models that reduces training time while preserving vital conditions for accurate modeling. However, we have identified a limitation in the training loss function used with t-batching. Through mathematical analysis, we propose two alternative loss functions that overcome these issues, resulting in enhanced training performance. We extensively evaluate the proposed loss functions on synthetic and real-world dynamic networks. The results consistently demonstrate superior performance compared to the original loss function. Notably, in a real-world network characterized by diverse user interaction histories, the proposed loss functions achieved more than 26.9% enhancement in Mean Reciprocal Rank (MRR) and more than 11.8% improvement in Recall@10. These findings underscore the efficacy of the proposed loss functions in dynamic network modeling., Comment: 29 pages, 10 figures, 4 tables, Submitted to Information Sciences

Social touch provides a rich non-verbal communication channel between humans and robots. Prior work has identified a set of touch gestures for human-robot interaction and described them with natural language labels (e.g., stroking, patting). Yet, no data exists on the semantic relationships between the touch gestures in users' minds. To endow robots with touch intelligence, we investigated how people perceive the similarities of social touch labels from the literature. In an online study, 45 participants grouped 36 social touch labels based on their perceived similarities and annotated their groupings with descriptive names. We derived quantitative similarities of the gestures from these groupings and analyzed the similarities using hierarchical clustering. The analysis resulted in 9 clusters of touch gestures formed around the social, emotional, and contact characteristics of the gestures. We discuss the implications of our results for designing and evaluating touch sensing and interactions with social robots., Comment: 8 pages